train
Cluster-GCN An Efficient Algorithm for Training Deep Convolution Networks
Chiang W., Liu X., Si S., Li Y., Bengio S. and Hsieh C. Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks. ......
Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA
一、项目背景 We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary ......
论文解读（VAT）《Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning》
论文信息 论文标题：Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning论文作者：Takeru Miyato, S. Maeda, Masanori Koya ......
论文解读《Do We Need Zero Training Loss After Achieving Zero Training Error?》
论文信息 论文标题：Do We Need Zero Training Loss After Achieving Zero Training Error?论文作者：Takashi Ishida, I. Yamane, Tomoya Sakai, Gang Niu, M. Sugiyama论文来源：20 ......
猛读论文13 |【CVPR 2022 UDA】Unleashing Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
动机 解决（1）对比学习管道中的增强通常会扭曲人物图像中的判别线索（2）细粒度的局部特征人物图像尚未得到充分探索。 思路 方法 ......
迁移学习（PAT）《Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation》
论文信息 论文标题：Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation论文作者：Weili Shi, Ronghang Zhu, Sheng Li论文来源：KDD 2022论文地址：dow ......
Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
Zou D., Hu Z., Wang Y., Jiang S., Sun Y. and Gu Q. Layer-dependent importance sampling for training deep and large graph convolutional networks. NIPS, ......
Train the Tesseract OCR engine[how to do]
Training the Tesseract OCR engine is a complex and time-consuming process that involves several steps. Here is an overview of the process: Prepare you ......
ziyi-lstm-train代码
lstm的train代码 def train_lstm(net,lr,train_loader,total_epoch): global_step = 1 optimizer = torch.optim.Adam(net.parameters(), lr=lr) scheduler = lr_sch ......
BUPT 2023 Spring Training #9
原题：2021“MINIEYE杯”中国大学生算法设计超级联赛（1） 卡在两道题上，然后就没有然后了 A 对于 $i \in [0,\lceil\frac n2\rceil-1] \cap {\mathbb Z}$，取模时一定可以取到（$n \equiv i({\rm mod}\ n-i)$） 对于 ......
GPT模型: Generative Pre-training 生成式无监督预训练
GPT，GPT-2，GPT-3 论文精读【论文精读】_哔哩哔哩_bilibili ELMo：将上下文当作特征，但是无监督的语料和我们真实的语料还是有区别的，不一定符合我们特定的任务，是一种双向的特征提取。 OpenAI GPT: 通过transformer decoder学习出来一个语言模型，不是固 ......
Stochastic Training of Graph Convolutional Networks with Variance Reduction
Chen J., Zhu J. and Song L. Stochastic training of graph convolutional networks with variance reduction. ICML, 2018. 概 我们都知道, GCN 虽然形式简单, 但是对于结点个数非常多的 ......
Generative Pre-trained Transformer（GPT）模型技术初探
一、Transformer模型 2017年，Google在论文 Attention is All you need 中提出了 Transformer 模型，其使用 Self-Attention 结构取代了在 NLP 任务中常用的 RNN 网络结构。相比 RNN 网络结构，其最大的优点是可以并行计算。 ......
HNU2019 Summer Training 3 E. Blurred Pictures
E. Blurred Pictures time limit per test 2 seconds memory limit per test 256 megabytes input standard input output standard output Damon loves to take ......
论文解读（ FGSM）《Adversarial training methods for semi-supervised text classification》
论文信息 论文标题：Adversarial training methods for semi-supervised text classification论文作者：Taekyung Kim论文来源：ICLR 2017论文地址：download 论文代码：download视屏讲解：click 1 背 ......
【IOI2017】Toy Train（博弈）
题目链接：https://uoj.ac/problem/322 分析 “一个点的出边一旦确定就不能改变”这个条件不好处理。通过网上一些题解的分析，可以把问题修改成： 结点的主人每次可以指定任意一条出边（即使之前已经指定了另外一条）。 A 胜利条件：存在一种策略，无论 B 怎么操作，总能使火车无限次经 ......
迁移学习《Asymmetric Tri-training for Unsupervised Domain Adaptation》
论文信息 论文标题：Asymmetric Tri-training for Unsupervised Domain Adaptation论文作者：Kuniaki Saito, Y. Ushiku, T. Harada论文来源：27 February 2017——ICML论文地址：download 论 ......
【829】sklearn中train_test_split函数中的random_state有什么用？
参考：sklearn.model_selection中train_test_split的坑 参考：sklearn中train_test_split函数中的random_state有什么用？ 对 random_state 设置一个固定的值，可以保证每次得到相同的训练集与测试集！ ......
「解题报告」ARC123E Training
挺有趣的题，为数不多的自己能切的题。 题意无非就是要你求 $i \in [1, n]$，有多少满足 $a + \lfloor\frac{i}{b} \rfloor = c + \lfloor\frac{i}{d}\rfloor$。 首先移项，得 $a - c = \lfloor\frac{i}{d} ......
KPCA matlab代码，可分train和test。 注释清晰
KPCA matlab代码，可分train和test。 注释清晰YID:7220647215929418 ......
Going Deeper With Directly-Trained Larger Spiking Neural Networks
郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) Abstract 脉冲神经网络（SNN）在时空信息和事件驱动信号处理的生物可编程编码中很有前途，非 ......
论文解读（Moco v3）《An Empirical Study of Training Self-Supervised Vision Transformers》
论文信息 论文标题：Improved Baselines with Momentum Contrastive Learning论文作者：Xinlei Chen, Saining Xie, Kaiming He论文来源：2021 ICCV论文地址：download 论文代码：download引用次数： ......
迁移学习（IIMT）——《Improve Unsupervised Domain Adaptation with Mixup Training》
论文信息 论文标题：Improve Unsupervised Domain Adaptation with Mixup Training论文作者：Shen Yan, Huan Song, Nanxiang Li, Lincan Zou, Liu Ren论文来源：arxiv 2020论文地址：down ......